One thought on “Gartner: Magic Quadrant for Data Center Networking

  1. Market — Data center networking provides network functions that support connectivity within enterprise data centers. Connectivity can be provided by physical switches, which comprise hardware and software and which may be acquired in bundled or unbundled form. However, with the emergence of network virtualization and new architectural models like software-defined networking, software overlays became an additional option in the market and are considered in this Magic Quadrant. Further information on the data center switching market can be found in Gartner’s Enterprise Network Equipment Market Share research.

    The data center networking market is primarily driven by three factors:

    1. Refresh of existing data center networking equipment that is at its technological or support limits (see “Know When It’s Time to Replace Enterprise Network Equipment” )

    2. The expansion of capacity (i.e., physical build-outs) within existing locations

    3. The desire to increase agility and automation to an existing data center

    Typical Buyers — Within the enterprise, CIOs, CTOs, VPs of I&O, directors of networking and network managers are typically the buyers of data center networking infrastructure. Personnel responsible for cloud infrastructure and data center automation are increasingly influencing personnel who are making buying decisions as well.

    How Buyers Shape Their Buying Decision — Data center networking equipment is business-critical and has a long life cycle, so buyers are strongly influenced by historical vendor relationships, experiences with the quality of their support and technical familiarity with previously installed products. In terms of feature/functionality, buyers typically focus on several factors, including performance, form-factor, deployment options, supplier availability and ease of management. They also focus on integration with higher-level infrastructure orchestration platforms, automation tools, programmability through an API, visibility/analytics, customer experience, brand visibility and overall solution architecture. In particular, automation, ease of management and the ability to support hybrid cloud use cases are increasingly important. Price, for both equipment and support, is also a factor, although not the main driver for most enterprise buyers.

    Deliverables — The most common deliverable is in the form of a switch (physical or virtual) or switching fabric, and the requisite management and control affiliated with the switches. The switches provide physical and logical data network connectivity for IT infrastructure residing in the data center (like servers, IP storage systems, security platforms and other network appliances). The most common network technology deployed in data centers is Ethernet, in all speed variants from 1 to 100 gigabits, with copper or fiber cables. Virtual network overlays are a more recent addition and provide logical connectivity over the physical network, leveraging virtual switches and creating virtual tunnels with protocols like VXLAN. Typical network functions include the ability to create virtual network segments and manage logical connectivity at Layer 2 (VLANs and VXLANs) and Layer 3 (IP routing). Some solutions are referred to as Ethernet fabrics and can be managed as a single logical entity through a GUI or API, rather than at the individual switch level, providing low-touch provisioning on its devices.

    How Providers Package, Market and Deliver — Buyers typically source their data center network: (1) directly from network equipment suppliers, or (2) via a reseller or system integrator. The data center network is normally purchased (capex) and maintained for a number of years under a support contract.

    In the last two years, we have seen a trend toward disaggregation of hardware and software in pricing. Alternative software options can often be selected for the same hardware platform, and some vendors propose perpetual software licenses and price software support separately from hardware support. These changes in pricing scheme show that value is shifting from hardware to software/services and impacting vendor’s revenue composition. Data center networking solutions can also be procured from some vendors via leasing, pay-as-you-grow or other consumption-based pricing models.
    ……………………………………………………………………………………………..

    Vendor Landscape Changes:

    Just a few years ago, almost every vendor in this research was a fierce head-to-head competitor. This is no longer the case, as there is a substantial degree of coopetition, with vendors both partnering and competing. There are numerous instances of this, with specific examples including:

    Dell EMC is the majority owner of VMware, owning 80+% of VMware stock.

    HPE maintains a 49% ownership in New H3C group, resells Arista and VMware data center networking products, and also supports running Big Switch Networks, Cumulus Networks and other vendors’ NOSs on its Altoline switches.

    Dell supports Cumulus Networks, Big Switch Networks, Pluribus Networks and other vendors’ software running on its switches.

    Mellanox Technologies supports the Cumulus Networks NOS (and others) running on its switches.

    Cumulus Networks has its own hardware, but also has integrated its software to run on HPE, Mellanox Technologies and Dell switches.

    VMware NSX runs on top of all vendors’ hardware, and it has performed specific hardware/overlay integration with most vendors in this research, including Arista Networks and Juniper Networks.

    Lenovo partners with Juniper Networks to fill out its data center networking portfolio, including the use of Contrail as an overlay solution.
    ………………………………………………………………………………………………..

    Extended Market Definition:

    Typical Business Outcomes — The primary business outcome is local connectivity within enterprise data centers, between servers, data center appliances (like firewalls and application delivery controllers), IP storage, and those network edge platforms that provide connectivity to the rest of the enterprise network or other data centers. This local connectivity is needed to support applications and services running in the data center.

    Physical interfaces: Physical interfaces to plug-in devices are a very common component of products in this market. 10G is now the most common interface speed we see in enterprise data center proposals. However, we are also rapidly seeing the introduction of new Ethernet connectivity options at higher speeds (25 GbE, 50 GbE and 100 GbE). Interface performance is rarely an issue for new implementations, and speeds and feeds are less relevant as buying criteria for the majority of enterprise clients, when compared to automation and ease of operations.

    Physical topology and switches: The spine-and-leaf (folded Clos) topology is the most common physical network design, proposed by most vendors. It has replaced the historical three-tier design (access, aggregation, core). The reduction in physical switching tiers is better-suited to support the massive east-west traffic flows created by new application architectures (see “Building Data Center Networks in the Digital Business Era” and “Simplify Your Data Center Network to Improve Performance and Decrease Costs” ). Vendors deliver a variety of physical form factors for their switches, including fixed-form factor and modular or chassis-based switches. In addition, this includes software-based switches such as virtual switches that reside inside of physical virtualized servers.

    Switching/infrastructure management: Ethernet fabric provides management for a collection of switches as a single construct, and programmable fabrics include an API. Fabrics are commonly adopted as logical control planes for spine-and-leaf designs, replacing legacy protocols like Spanning Tree Protocol (STP) and enabling better utilization of all the available paths. Fabrics automate several tasks affiliated with managing a data center switching infrastructure, including autodiscovery of switches, autoconfiguration of switches, etc. (see “Innovation Insight for Ethernet Switching Fabric” ).

    Automation and orchestration: Automation and orchestration are increasingly important to buyers in this market, because enterprises want to improve speed to deliver data center network infrastructure to business, including on-demand capability. This includes support and integration with popular automation tools (such as Ansible, Chef and Puppet), integration with broader platforms like VMware vRA, inclusion of published/open APIs, as well as support for scripting tools like Python (see “Building Data Center Networks in the Digital Business Era” ).

    Network overlays: Network overlays create a logical topology abstracted from the underlying physical topology. We see overlay tunneling protocols like VXLAN used with virtual switches to provide Layer 2 connectivity on top of scalable Layer 3 spine-and-leaf designs, enabling support of multiple tenants and more granular network partitioning (microsegmentation), to increase security within the data center. Overlay products also typically provide an API to enable programmability and integration with orchestration platforms.

    Public cloud extension/hybrid cloud: An emerging capability of data center products is the ability to provide visibility, troubleshooting, configuration and management for workloads that exist in a public cloud provider’s infrastructure. In this case, vendors are not providing the underlying physical infrastructure within the cloud provider network, but provide capability to manage that infrastructure in a consistent manner with on-premises/colocated workloads.

Comments are closed.